Cleanup

generator/audio_assets.py

@@ -0,0 +1,68 @@
+"""Validate and copy supplied recordings without synthesis or transformation."""
+from __future__ import annotations
+
+import fractions
+import hashlib
+import json
+import re
+import shutil
+import wave
+
+import generator.model
+import generator.performance
+
+TEMPOS = tuple(range(60, 121, 10))
+
+def describe_wav(path, root, *, song_id='', bpm=0):
+  if path.is_symlink() or not path.is_file() or not path.resolve().is_relative_to(root.resolve()):
+    raise ValueError(f'{path}: expected a contained regular WAV')
+  try:
+    with wave.open(str(path), 'rb') as audio:
+      channels, rate, frames = audio.getnchannels(), audio.getframerate(), audio.getnframes()
+      if audio.getcomptype() != 'NONE' or audio.getsampwidth() != 2 or channels not in (1, 2) or not 8000 <= rate <= 192000 or frames <= 0:
+        raise ValueError('expected nonempty mono/stereo PCM16 WAV')
+      remaining = frames
+      while remaining:
+        count = min(remaining, 65536)
+        if len(audio.readframes(count)) != count * channels * 2:
+          raise ValueError('truncated WAV data')
+        remaining -= count
+  except (wave.Error, EOFError) as error:
+    raise ValueError(f'{path}: invalid WAV: {error}') from error
+  with path.open('rb') as source:
+    digest = hashlib.file_digest(source, 'sha256').hexdigest()
+  return dict(path=path.relative_to(root).as_posix(), sha256=digest, channels=channels, sample_rate=rate, frames=frames, song_id=song_id, bpm=bpm)
+
+def copy_audio(static, destination, song_ids):
+  entries = []
+  inputs = [(static / 'sounds' / name, '', 0) for name in ('beat1.wav', 'beat2.wav')]
+  for path in sorted((static / 'backing').glob('*.wav')):
+    match = re.fullmatch(r'([a-z0-9]+(?:_[a-z0-9]+)*)_(60|70|80|90|100|110|120)\.wav', path.name)
+    if not match:
+      raise ValueError(f'{path}: unsupported backing filename or tempo')
+    if match[1] not in song_ids:
+      continue
+    inputs.append((path, match[1], int(match[2])))
+  for source, song_id, bpm in inputs:
+    description = describe_wav(source, static, song_id=song_id, bpm=bpm)
+    target = destination / description['path']
+    target.parent.mkdir(parents=True, exist_ok=True)
+    shutil.copyfile(source, target)
+    entries.append(description)
+  return entries
+
+def validate_recording_lengths(root, entries):
+  durations = {}
+  for path in sorted((root / 'songs').glob('*.json')):
+    document = json.loads(path.read_text())
+    performance = generator.performance.timing(document)
+    song_id = performance['song_id']
+    duration = generator.model.fraction(performance['duration']) + performance['count_in_beats']
+    if song_id in durations and durations[song_id] != duration:
+      raise ValueError(f'{song_id}: parts disagree about performance duration')
+    durations[song_id] = duration
+  for entry in entries:
+    if entry['song_id']:
+      seconds = fractions.Fraction(entry['frames'], entry['sample_rate'])
+      if seconds < durations[entry['song_id']] * 60 / entry['bpm']:
+        raise ValueError(f"{entry['path']}: backing recording is shorter than count-in and score")